尝试在 Keras 中拟合模型时如何修复失败的断言“输出通道应按组整除”？

Question

我正在尝试将 ImageDataGenerator() 用于我的图像数据集。 这是我的图像增强代码：

batch_size = 16

train_datagen = ImageDataGenerator(
        rescale=1./255,
        shear_range=0.2,
        zoom_range=0.2,
        horizontal_flip=True)

test_datagen = ImageDataGenerator(rescale=1./255)

# Use flow from dataframe
train_generator = train_datagen.flow_from_dataframe(
        dataframe=train,
        directory="data/train",
        x_col="id",
        y_col=["not_ready", "ready"],
        target_size=(300, 300),
        batch_size=batch_size,
        class_mode="raw",
        validate_filenames=False)

validation_generator = test_datagen.flow_from_dataframe(
        dataframe=validation,
        directory="data/validation",
        x_col="id",
        y_col=["not_ready", "ready"],
        target_size=(300, 300),
        batch_size=batch_size,
        class_mode="raw",
        validate_filenames=False)

然后将该插件用于我的模型：

model = Sequential([
    layers.Conv2D(filters=16, kernel_size=(3, 3), activation='relu', input_shape=(300, 300, 1)),
    layers.MaxPooling2D(pool_size=(2, 2)),
    layers.Dropout(0.5),
    layers.Conv2D(filters=32, kernel_size=(3, 3), activation='relu'),
    layers.MaxPooling2D(pool_size=(2, 2)),
    layers.Dropout(0.5),
    layers.Flatten(),
    layers.Dense(64, activation='relu'),
    layers.Dropout(0.5),
    layers.Dense(32, activation='relu'),
    layers.Dropout(0.5),
    layers.Dense(2, activation='sigmoid')
])

使用 EarlyStopping：

early_stopping = EarlyStopping(monitor='val_loss',mode='min',verbose=1,patience=10, restore_best_weights=True)

编译并拟合模型：

model.compile(optimizer=Adam(), loss='binary_crossentropy', metrics=['accuracy'])
history = model.fit(
        train_generator,
        steps_per_epoch=train_generator.n // batch_size,
        epochs=100,
        validation_data=validation_generator,
        validation_steps=validation_generator.n // batch_size,
        callbacks=[early_stopping])

那是代码崩溃的时候，给出了这个错误信息。

/AppleInternal/Library/BuildRoots/8d3bda53-8d9c-11ec-abd7-fa6a1964e34e/Library/Caches/com.apple.xbs/Sources/MetalPerformanceShaders/MPSNDArray/Kernels/MPSNDArrayConvolution.mm:2317: failed assertion `output channels should be divisible by group'

我尝试更改输出神经元，但这不起作用。我不知道该怎么办了。请帮我。非常感谢。

Answer 1

知道了。因为我使用灰度图像。所以我必须在 flow_from_dataframe() 中添加 color_mode 关键字参数并将其设置为等于 "grayscale"

train_generator = train_datagen.flow_from_dataframe(
        dataframe=train,
        directory="data/train",
        x_col="id",
        y_col=["not_ready", "ready"],
        target_size=(300, 300),
        batch_size=batch_size,
        class_mode="raw",
        color_mode="grayscale")

validation_generator = test_datagen.flow_from_dataframe(
        dataframe=validation,
        directory="data/validation",
        x_col="id",
        y_col=["not_ready", "ready"],
        target_size=(300, 300),
        batch_size=batch_size,
        class_mode="raw",
        color_mode="grayscale")

尝试在 Keras 中拟合模型时如何修复失败的断言“输出通道应按组整除”？

How to fix failed assertion `output channels should be divisible by group' when trying to fit the model in Keras?

python

keras

tensorflow

data-augmentation